Tcs Hiring AI Engineer-AI and Automation E2||Generative AI E3

Job Title- AI Engineer

Job

Requirements

Generative AI & LLMs • Hands-on experience with: o GPT models o Azure OpenAI o OpenAI APIs o Anthropic Claude o Google Gemini o Llama models • Experience implementing: o Prompt Engineering o Function Calling o Tool Usage o Structured Outputs • Knowledge of AI evaluation frameworks and responsible AI principles. Retrieval-Augmented Generation (RAG) • Experience designing and implementing RAG architectures. • Knowledge of: o Embedding models o Semantic search o Vector databases • Hands-on experience with: o Azure AI Search o Pinecone o Weaviate o ChromaDB o FAISS • Experience in document ingestion, chunking, indexing, and retrieval strategies. AI Agents & Orchestration • Experience building multi-step AI workflows and autonomous agents.

Familiarity with: o LangChain o LangGraph o Semantic Kernel o AutoGen o CrewAI • Experience integrating external tools, APIs, and enterprise systems into AI agents. Cloud & DevOps • Experience with cloud platforms: o Microsoft Azure (preferred) o AWS o Google Cloud Platform • Hands-on experience with: o Docker o Kubernetes o CI/CD pipelines o Infrastructure as Code • Experience deploying AI services and scalable web applications. Data & Databases • Strong SQL skills. • Understanding of data modeling and ETL processes. Security & Governance • Knowledge of: o OAuth o OpenID Connect o Azure Entra ID (Azure AD) • Understanding of AI security, data privacy, and compliance requirements. • Experience implementing secure authentication and authorization.

Key

Responsibilities- Design, develop, and maintain end-to-end AI-powered applications. • Build scalable and secure full-stack solutions that integrate Generative AI capabilities. • Translate business requirements into AI-enabled products and services. Generative AI & LLM Integration • Integrate Large Language Models (LLMs) into enterprise applications. • Develop advanced prompt engineering techniques to improve AI response quality.

Implement function calling, tool integrations, and structured AI workflows. • Monitor and optimize model performance, latency, and cost Retrieval-Augmented Generation (RAG) • Design and implement RAG architectures for enterprise knowledge retrieval. • Build document ingestion, chunking, embedding, indexing, and retrieval pipelines. • Optimize search relevance, grounding accuracy, and response quality. AI Agent Development • Develop intelligent AI agents capable of complex reasoning and task orchestration. • Integrate agents with APIs, databases, enterprise applications, and third-party services. • Implement multi-agent systems and workflow automation solutions. Full-Stack Application Development • Develop responsive user interfaces using modern frontend frameworks. • Build scalable backend services, APIs, and microservices. • Ensure application performance, reliability, and maintainability. Cloud & Deployment • Deploy AI applications using Azure, AWS, or GCP cloud services. • Implement CI/CD pipelines for automated testing and deployment. • Manage containerized workloads using Docker and Kubernetes. • Monitor application health, performance, and scalability. Collaboration & Innovation • Collaborate with Product Managers, Data Scientists, Architects, and Business Stakeholders. • Conduct technical design reviews and code reviews. • Evaluate emerging AI technologies and recommend innovative solutions.

Mentor junior engineers and contribute to engineering best practices.